Menu
▾
▴
Re: [BProc] bjs job id
|
From: Daniel G. <dg...@ti...> - 2004-03-18 04:13:25
|
Thanks, Erik. It works just fine. The issue with the interactive
jobs is also fixed.
I guess it is worth at least a minor revision number... :-)
Regards,
Daniel
On Wed, Mar 17, 2004 at 03:22:23PM -0700, er...@he... wrote:
> On Wed, Mar 17, 2004 at 04:45:55PM -0500, Daniel Gruner wrote:
> > Hi Erik,
> >
> > Would you care to actually send me your proposed diffs? I have been
> > trying to make sense of your code, but... :-)
>
> Ok, ok :) I had my head in BJS today anyway for another reason. It
> turned out to be a little more involved than what I said below because
> bjs wasn't even sending the job ID to bjssub in the interactive case.
> There's a few other bug fixes in there too. See the ChangeLog part of
> the diff for details on that. The environment variable is
> "BJS_JOBID". Note that BJS_JOBIDs may be re-used if bjs is restarted.
>
> - Erik
>
> > On Wed, Mar 17, 2004 at 12:46:15PM -0700, er...@he... wrote:
> > > On Wed, Mar 17, 2004 at 11:36:56AM -0500, Daniel Gruner wrote:
> > > > HI
> > > >
> > > > Is there an environment variable setup by bjs such that the submitted
> > > > script can know its id? I know the $NODES variable is set by bjs, but
> > > > it would be useful to also have the JOBID set in the environment, so that
> > > > one can set up individual directories based on the JOBID, etc.
> > >
> > > It doesn't. That's a good idea though. I think it could be added
> > > with two lines in bjs.c:bjs_job_environment() and the analagous spot
> > > (where NODES is set) in bjssub.c.
> > >
> > > - Erik
>
>
> Index: ChangeLog
> ===================================================================
> RCS file: /home/repository/bjs/ChangeLog,v
> retrieving revision 1.7
> retrieving revision 1.10
> diff -u -r1.7 -r1.10
> --- ChangeLog 10 Nov 2003 19:48:15 -0000 1.7
> +++ ChangeLog 17 Mar 2004 22:41:45 -0000 1.10
> @@ -1,3 +1,16 @@
> +Changes from 1.4 to
> +
> + * Fixed signal setup for batch mode jobs started by the daemons.
> + Signal handling options and signal masks are now properly reset to
> + defaults for the child processes.
> +
> + * Fixed signal handling behavior in the daemon so that the daemon
> + won't get slain by SIGPIPE.
> +
> + * Fixed a problem with node ranges not getting assigned properly.
> +
> + * Added BJS_JOBID environment variable.
> +
> Changes from 1.3 to 1.4
>
> * Updated to work reasonably on x86_64 machines.
> Index: bjs.c
> ===================================================================
> RCS file: /home/repository/bjs/bjs.c,v
> retrieving revision 1.27
> retrieving revision 1.30
> diff -u -r1.27 -r1.30
> --- bjs.c 10 Nov 2003 19:48:15 -0000 1.27
> +++ bjs.c 17 Mar 2004 22:41:45 -0000 1.30
> @@ -24,7 +24,7 @@
> * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public
> * License for more detail.
> *
> - * $Id: bjs.c,v 1.27 2003/11/10 19:48:15 hendriks Exp $
> + * $Id: bjs.c,v 1.30 2004/03/17 22:41:45 hendriks Exp $
> *--------------------------------------------------------------------*/
> #include <stdio.h>
> #include <stdlib.h>
> @@ -318,10 +318,10 @@
>
> static struct bproc_node_set_t clean_set = BPROC_EMPTY_NODESET;
> void bjs_do_clean(void) {
> +#if 1
> int i, j, nprocs, killed_one;
> struct bproc_proc_info_t *plist;
>
> -
> /* XXX It would be much better if we had the option of killing
> * only the processes related to the job. We're going to end up
> * killing off mon, etc. here. */
> @@ -340,6 +340,9 @@
>
> if (nprocs > 0) free(plist);
> } while(killed_one);
> +#else
> +#warning "bjs_do_clean is commented out!!!!"
> +#endif
>
> bproc_nodeset_free(&clean_set);
> }
> @@ -435,6 +438,9 @@
> tmp[len-1] = 0;
> printf("NODES=\"%s\"\n", tmp); fflush(0);
> setenv("NODES", tmp, 1);
> +
> + sprintf(tmp, "%d", j->job_id);
> + setenv("BJS_JOBID", tmp, 1);
> }
>
> static
> @@ -524,8 +530,18 @@
> return -1;
> }
> if (pid == 0) {
> - /* Close file descriptors for clients */
> struct list_head *l;
> + sigset_t sset;
> +
> + /* Restore signal handling defaults */
> + signal(SIGCHLD, SIG_DFL);
> + signal(SIGHUP, SIG_DFL);
> + signal(SIGPIPE, SIG_IGN);
> +
> + sigfillset(&sset);
> + sigprocmask(SIG_UNBLOCK, &sset, 0);
> +
> + /* Close file descriptors for clients */
> for (l=clients.next; l != &clients; l = l->next) {
> struct client_t *c;
> c = list_entry(l, struct client_t, list);
> @@ -572,6 +588,8 @@
> char tmp[20];
>
> sx = sexp_create_list("nodes", 0);
> + sprintf(tmp, "%d", j->job_id);
> + sexp_append_atom(sx, tmp);
> for (l = j->nodes.next; l != &j->nodes; l = l->next) {
> struct node_alloc_t *n = list_entry(l,struct node_alloc_t,nodes_list);
> sprintf(tmp, "%d", bjs_node_idx[n->node]->node);
> @@ -1617,61 +1635,6 @@
> return current_pool;
> }
>
> -#if 0
> -static
> -int do_nodelist(char *str_, int **numlist_) {
> - char *end1, *end2, *next, *str;
> - int num1, num2, i;
> - int numlist_len = 0;
> - int *numlist = 0;
> -
> - for (str = str_; *str; str = next) {
> - /* Look for a number */
> - num1 = strtol(str, &end1, 0);
> - switch (*end1) {
> - case 0:
> - num2 = num1;
> - next = end1;
> - break;
> - case ',':
> - num2 = num1;
> - next = end1+1;
> - break;
> - case '-':
> - num2 = strtol(end1+1, &end2, 0);
> - if (end2 == end1+1) {
> - if (numlist) free(numlist);
> - return -1;
> - }
> - switch (*end2) {
> - case 0:
> - next = end2;
> - break;
> - case ',':
> - next = end2+1;
> - break;
> - default:
> - if (numlist) free(numlist);
> - return -1;
> - }
> - break;
> - default:
> - if (numlist) free(numlist);
> - return -1;
> - }
> -
> - /* Fill in range */
> - numlist = realloc_chk(numlist,
> - sizeof(int) * (numlist_len + num2 - num1 + 1));
> - for (i = num1; i <= num2; i++)
> - numlist[numlist_len++] = i;
> - }
> -
> - * numlist_ = numlist;
> - return numlist_len;
> -}
> -#endif
> -
> static
> int config_nodes_callback(struct cmconf *cnf, char **args) {
> int i, j;
> @@ -1694,14 +1657,12 @@
> return -1;
> }
>
> - /*printf("%d %d %s\n", p->nnodes, ns2.size, args[i]);*/
> -
> p->nodes = realloc_chk(p->nodes, sizeof(int) * (p->nnodes + ns2.size));
> for (j=0; j < ns2.size; j++) {
> /* XXX Do we want to sanity check node numbers at this
> * point? It seems that we need to be able to handle
> * bogus node numbers. */
> - p->nodes[p->nnodes++] = ns.node[j].node;
> + p->nodes[p->nnodes++] = ns2.node[j].node;
> /* We handle machine setup inside config_xfer */
> }
> bproc_nodeset_free(&ns);
> @@ -2398,6 +2359,7 @@
> "Usage: %s [options...]\n"
> " -h Print this message and exit.\n"
> " -V Print version information and exit.\n"
> +" -v Increase verbose level.\n"
> " -C file Read configuration from file (default=%s)\n"
> , arg0, DEFAULT_CONFIG_FILE);
> }
> @@ -2474,7 +2436,7 @@
> sigprocmask(SIG_BLOCK, &sset, 0);
> signal(SIGCHLD, signal_handler);
> signal(SIGHUP, signal_handler);
> - //signal(SIGPIPE, SIG_IGN);
> + signal(SIGPIPE, SIG_IGN);
>
> /*-- main select loop ------------------------------------------*/
> while (1) {
> Index: bjssub.c
> ===================================================================
> RCS file: /home/repository/bjs/bjssub.c,v
> retrieving revision 1.12
> retrieving revision 1.13
> diff -u -r1.12 -r1.13
> --- bjssub.c 19 Sep 2002 20:28:20 -0000 1.12
> +++ bjssub.c 17 Mar 2004 22:41:45 -0000 1.13
> @@ -24,7 +24,7 @@
> * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public
> * License for more detail.
> *
> - * $Id: bjssub.c,v 1.12 2002/09/19 20:28:20 hendriks Exp $
> + * $Id: bjssub.c,v 1.13 2004/03/17 22:41:45 hendriks Exp $
> *--------------------------------------------------------------------*/
> #include <stdio.h>
> #include <stdlib.h>
> @@ -292,16 +292,19 @@
>
> /* Put together the nodes string and stick it in the environment */
> len = 0;
> - for (sx = nodesx->list->next; sx; sx=sx->next)
> + for (sx = nodesx->list->next->next; sx; sx=sx->next)
> len += strlen(sx->val) + 1;
> nodesstr = alloca(len);
> nodesstr[0] = 0;
> - for (sx = nodesx->list->next; sx; sx=sx->next) {
> + for (sx = nodesx->list->next->next; sx; sx=sx->next) {
> strcat(nodesstr, sx->val);
> if (sx->next) strcat(nodesstr, ",");
> }
> setenv("NODES", nodesstr, 1);
> printf("NODES=%s\n", nodesstr);
> +
> + setenv("BJS_JOBID", nodesx->list->next->val, 1);
> + printf("BJS_JOBID=%s\n", nodesx->list->next->val);
>
> if (pwd && chdir(pwd)) {
> fprintf(stderr, "chdir(\"%s\"): %s\n", pwd, strerror(errno));
> Index: sexps.txt
> ===================================================================
> RCS file: /home/repository/bjs/sexps.txt,v
> retrieving revision 1.3
> retrieving revision 1.4
> diff -u -r1.3 -r1.4
> --- sexps.txt 17 Sep 2002 03:55:10 -0000 1.3
> +++ sexps.txt 17 Mar 2004 22:41:45 -0000 1.4
> @@ -20,7 +20,7 @@
>
> Job submission (interactive) responses:
> (ok ID)
> -(nodes NODE ...)
> +(nodes ID NODE ...)
> (error MSG)
>
>
--
Dr. Daniel Gruner dg...@ti...
Dept. of Chemistry dan...@ut...
University of Toronto phone: (416)-978-8689
80 St. George Street fax: (416)-978-5325
Toronto, ON M5S 3H6, Canada finger for PGP public key
|
